Machine Learning Engineer – ML Evaluation & Experiment Design
New
A
Anyone AISoftware Engineering / AI
Argentina - Fully Remote; Uruguay, Chile, Ecuador - Fully Remote; Portugal; Mexico - Fully Remote; Colombia - Fully Remote; Spain; BrazilContractMiddle
Salary65 USD per hour
Apply NowOpens the employer's application page
Job Details
- Experience
- 3+ years
- Required Skills
- Machine LearningDebugging
Requirements
- 3+ years of hands-on applied machine learning experience.
- Strong proficiency in ML experiment design, model selection, and hyperparameter tuning.
- Expertise in data preprocessing, validation, and managing train/validation/test splits.
- Ability to identify data leakage, label noise, distribution shift, and spurious correlations.
- Experience evaluating the statistical significance of model performance improvements.
- Deep understanding of ML evaluation metrics and appropriate use cases.
- Experience debugging ML workloads across CPU and GPU environments.
- Strong analytical skills with the ability to provide clear written technical feedback.
- Understanding of ML failure modes like Goodhart’s Law, Simpson’s paradox, and metric gaming.
Responsibilities
- Review ML challenges to determine if they are well designed and technically solvable.
- Evaluate datasets for meaningful, learnable signals and identify synthetic data artifacts.
- Detect unintended shortcuts, data leakage, and evaluation flaws in ML pipelines.
- Verify reproducibility across the entire data-to-model-to-evaluation workflow.
- Assess and calibrate challenge difficulty to ensure they reward strong ML reasoning.
- Provide clear recommendations for improving or excluding problematic tasks.
View Full Description & ApplyYou'll be redirected to the employer's site
